SOC is estimated based on a battery model and Kalman filtering, with an accuracy of up to ±2%. This enables high-precision prediction of remaining battery capacity, helping to improve range performance.

Cloud-to-edge algorithms based on big data enable online identification of model parameters, achieving ±3 % SOH accuracy for precise insight into battery health.

Cell voltage accuracy ±2 mV; total current ±0.5 % @RD. Total voltage and current are synchronized at 1 ms, with total and individual cell voltages synchronized at 10 ms, enhancing algorithm precision.

Supports A/B partition dual-redundant over-the-air updates and code rollback, providing a seamless and reliable upgrade experience.

Enables bidirectional daisy-chain communication, enhancing data reliability and system robustness, ensuring foundational communications remain dependable.

Main control architecture implements high-low voltage sampling isolation, improving electrical safety and reducing failure rates.

Leverages standard-compliant big data to identify user driving habits and customize power algorithms, balancing performance and range requirements.

Tailors charging strategies based on user charging scenarios and driving schedules, optimizing charging time, cost, and battery lifespan.

Delivers personalized battery algorithm services while ensuring battery performance and longevity, enhancing user experience and interaction.